TY - GEN
T1 - Peer influence and homophily in the diffusion of the iphone 3G in a very large social network
AU - Matos, Miguel Godinho de
AU - Ferreira, Pedro A.
AU - Krackhardt, David
N1 - Copyright:
Copyright 2013 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - This paper studies the effects of peer influence and homophily on the diffusion of the iPhone 3G across a number of communities sampled from a large dataset from a major European Mobile carrier in one country. We use Stochastic Actor Based Models to capture the co-evolution of the social network as well as the dynamics of adoption. This helps to separate the roles of homophily and peer influence in the process of diffusion. We provide evidence that the propensity of a subscriber to adopt, when she is called upon to make a decision about whether she should adopt, increases with the number of friends that have already adopted. A one standard deviation increase above the mean in the number of friends that had already adopted increases the likelihood odds of adoption relative to no adoption by a factor of 2.8. The effect of peer influence is robust across a number of different specifications. The results for the effect of homophily are less clear. While, on average, we find a positive significant effect of adoption on tie formation, in many communities this effect is significant and negative and in others there is no effect at all.
AB - This paper studies the effects of peer influence and homophily on the diffusion of the iPhone 3G across a number of communities sampled from a large dataset from a major European Mobile carrier in one country. We use Stochastic Actor Based Models to capture the co-evolution of the social network as well as the dynamics of adoption. This helps to separate the roles of homophily and peer influence in the process of diffusion. We provide evidence that the propensity of a subscriber to adopt, when she is called upon to make a decision about whether she should adopt, increases with the number of friends that have already adopted. A one standard deviation increase above the mean in the number of friends that had already adopted increases the likelihood odds of adoption relative to no adoption by a factor of 2.8. The effect of peer influence is robust across a number of different specifications. The results for the effect of homophily are less clear. While, on average, we find a positive significant effect of adoption on tie formation, in many communities this effect is significant and negative and in others there is no effect at all.
KW - Diffusion
KW - Peer influence
KW - Siena
KW - Social networks
KW - Stochastic actor based models
UR - http://www.scopus.com/inward/record.url?scp=84873623063&partnerID=8YFLogxK
U2 - 10.1109/SocialCom-PASSAT.2012.32
DO - 10.1109/SocialCom-PASSAT.2012.32
M3 - Conference contribution
AN - SCOPUS:84873623063
SN - 9780769548487
T3 - Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012
SP - 134
EP - 143
BT - Proceedings - 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE/IEEE International Conference on Social Computing, SocialCom/PASSAT 2012
T2 - 2012 ASE/IEEE International Conference on Social Computing, SocialCom 2012 and the 2012 ASE/IEEE International Conference on Privacy, Security, Risk and Trust, PASSAT 2012
Y2 - 3 September 2012 through 5 September 2012
ER -